With a new artificial intelligence (AI) algorithm, planning for radiation therapy procedures could be completed in hours instead of days, according to researchers from the University of Toronto.
Engineering researchers led by Aaron Babier have developed an AI algorithm that mines historical radiation therapy data, which is then used by an optimization engine to develop treatment plans. In testing on 217 patients with throat cancer, the AI software generated therapy plans -- in just 20 minutes -- that yielded comparable results to conventionally planned treatments, according to the researchers.
They emphasized, though, that a radiation physicist would still need to review and further customize AI-developed treatment plans. This process could take a few hours.
"It is very much like automating the design process of a custom-made suit," senior author Timothy Chan, PhD, said in a statement from the University of Toronto Faculty of Applied Science and Engineering. "The tailor must first construct the suit based on the customer's measurements, then alter the suit here and there to achieve the best fit. Our tool goes through a similar process to construct the most effective radiation plan for each patient."
The researchers shared their work in an article published in the July issue of Medical Physics.
